DT-GWO: A hybrid decision tree and GWO-based algorithm for multi-objective task scheduling optimization in cloud computing

Abstract

Cloud computing faces significant challenges in task management, particularly in balancing server loads to prevent both overload and underload conditions while meeting diverse quality of service requirements. The need to manage multiple criteria further increases the complexity of this problem. Additionally, the heterogeneity of cloud resources often complicates efficient task scheduling. To overcome these challenges, this paper introduces a hybrid model that integrates the decision tree approach with the Grey Wolf Optimization (GWO) algorithm for the scheduling of independent tasks. The model aims to optimize makespan, reduce total cost, enhance resource utilization, and maintain load balance. In the proposed approach, tasks are first classified using a decision tree, after which the GWO algorithm allocates resources to the selected tasks. Simulations are conducted using the CloudSim toolkit, in a heterogeneous environment. The experiments consider various input scenarios, ranging from 200 to 3200 tasks. Compared to the standalone GWO algorithm, the proposed DT-GWO hybrid model achieves improvements of at least 18.5 % in makespan, 3.4 % in average resource utilization, and 12.7 % in total cost, all while maintaining load balance.